Recognition of petechia tongue based on log and gabor feature with spatial information

Authors:
Yangyang Zhao;Xiaoqiang Li;Zhicheng Fu
Affiliations:
School of Computer Engineering and Science, Shanghai University, China;School of Computer Engineering and Science, Shanghai University, China;School of Computer Engineering and Science, Shanghai University, China
Venue:
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Year:
2012

Citing 6
Cited 0

Texture Features for Browsing and Retrieval of Image Data

IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Computerized Method For Tongue Classification

ISDA '06 Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications - Volume 02
Tongue image analysis for appendicitis diagnosis

Information Sciences: an International Journal
A Feature Extraction Method for Recognition of Petechia Dot in Tongue Image

ICISE '09 Proceedings of the 2009 First IEEE International Conference on Information Science and Engineering
Robust lip segmentation method based on level set model

PCM'10 Proceedings of the 11th Pacific Rim conference on Advances in multimedia information processing: Part I
Detecting Wide Lines Using Isotropic Nonlinear Filtering

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognition of petechia tongue is still a challenging problem due to different color, morphology and texture in tongue image. This paper presents a new method to automatically recognition of petechia tongue based on LoG and Gabor feature with spatial information. The proposed approach begins with a normalized LoG filter to locate the suspected petechia areas in tongue image. In the subsequent step, the spatial position feature and Gabor feature were extracted as a feature descriptor of these regions. Support vector machine is used as a classifier to classify these suspected petechia areas into petechia and non-petechia areas. Finally, the proposed method judge whether the tongue image have petechia according to the proportion of petechia regions to all suspected petechia regions. Experimental results on two hundred tongue images indicate the better performance of our method, the accuracy achieves to 84.91%.